{"id":"https://openalex.org/W4200480415","doi":"https://doi.org/10.1109/hpec49654.2021.9622813","title":"Performance Study of GPU applications using SYCL and CUDA on Tesla V100 GPU","display_name":"Performance Study of GPU applications using SYCL and CUDA on Tesla V100 GPU","publication_year":2021,"publication_date":"2021-09-20","ids":{"openalex":"https://openalex.org/W4200480415","doi":"https://doi.org/10.1109/hpec49654.2021.9622813"},"language":"en","primary_location":{"id":"doi:10.1109/hpec49654.2021.9622813","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071358621","display_name":"Goutham Kalikrishna Reddy Kuncham","orcid":"https://orcid.org/0000-0003-2112-4769"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Goutham Kalikrishna Reddy Kuncham","raw_affiliation_strings":["NextGen R&D, Tata Consultancy Services, India"],"affiliations":[{"raw_affiliation_string":"NextGen R&D, Tata Consultancy Services, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034404374","display_name":"Rahul Vaidya","orcid":"https://orcid.org/0000-0001-6870-6091"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rahul Vaidya","raw_affiliation_strings":["NextGen R&D, Tata Consultancy Services, India"],"affiliations":[{"raw_affiliation_string":"NextGen R&D, Tata Consultancy Services, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076144651","display_name":"Mahesh Barve","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mahesh Barve","raw_affiliation_strings":["HPC Center Of Excellence, Tata Consultancy Services, India"],"affiliations":[{"raw_affiliation_string":"HPC Center Of Excellence, Tata Consultancy Services, India","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071358621"],"corresponding_institution_ids":["https://openalex.org/I55215948"],"apc_list":null,"apc_paid":null,"fwci":2.9937,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.91653518,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.837640643119812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7611733675003052},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.6037552356719971},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5167721509933472},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4559226334095001},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3942720293998718},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.25813621282577515},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.12782219052314758}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.837640643119812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7611733675003052},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.6037552356719971},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5167721509933472},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4559226334095001},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3942720293998718},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.25813621282577515},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.12782219052314758}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec49654.2021.9622813","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1997162567","https://openalex.org/W2018408367","https://openalex.org/W2078994750","https://openalex.org/W2080592089","https://openalex.org/W2291092806","https://openalex.org/W2582335504","https://openalex.org/W2954287266","https://openalex.org/W2997549515","https://openalex.org/W2998114460","https://openalex.org/W3011794212","https://openalex.org/W3039426601","https://openalex.org/W3125565132","https://openalex.org/W4253053747"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W1656096860","https://openalex.org/W1984739956"],"abstract_inverted_index":{"SYCL":[0,19,28,50,86,129],"standard":[1],"enables":[2],"single-source":[3],"programs":[4],"to":[5,106,134],"run":[6],"on":[7,39,51],"heterogeneous":[8],"platforms":[9],"consisting":[10],"of":[11,33,49,80,112,128],"CPUs,":[12],"GPUs,":[13],"FPGAs":[14],"across":[15],"different":[16],"hardware":[17],"vendors.":[18],"combines":[20],"modern":[21],"C++":[22],"features":[23,64],"along":[24],"with":[25],"OpenCL\u2019s":[26],"portability.":[27],"runtime":[29],"is":[30,72],"also":[31],"capable":[32],"targeting":[34],"the":[35,47,70,78,81,108,126],"CUDA":[36,131,141],"backend":[37],"directly":[38],"NVIDIA":[40,52,55],"GPUs.":[41],"This":[42],"approach":[43],"can":[44,57],"potentially":[45],"improve":[46],"performance":[48,71,79,90,109,127],"devices.":[53],"Although":[54],"GPUs":[56],"be":[58,135],"targeted":[59],"via":[60],"OpenCL":[61],"backend,":[62],"their":[63],"and":[65,69,87,99,120,130],"capabilities":[66],"are":[67],"limited,":[68],"inadequate.In":[73],"this":[74],"study,":[75,125],"we":[76,92],"compare":[77],"Nvidia":[82],"V100":[83],"GPU":[84,95],"using":[85],"CUDA.":[88],"For":[89],"evaluation,":[91],"selected":[93],"three":[94],"applications:":[96],"BabelStream,":[97],"Mixbench,":[98],"Tiled":[100],"Matrix-Multiplication.":[101],"We":[102],"conducted":[103],"extensive":[104],"tests":[105],"understand":[107],"in":[110,138],"terms":[111],"DRAM":[113],"bandwidth,":[114],"kernel":[115],"execution":[116],"time,":[117,119],"compilation":[118],"throughput.":[121],"As":[122],"per":[123],"our":[124],"were":[132],"found":[133],"similar.":[136],"However,":[137],"some":[139],"cases,":[140],"outperformed":[142],"SYCL.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}